Last refreshed 2026-05-01. Next refresh: weekly.
Why use Seed-OSS 36B Instruct on NVIDIA NIM?
NVIDIA NIM offers Seed-OSS 36B Instruct with competitive pricing. NVIDIA NIM is NVIDIA's deployment platform for GPU-accelerated inference microservices.
Input / 1M
-
Output / 1M
-
Cache
Not sourced
Batch
Not sourced
Setup recipe
Docs fallbackInstall
Use the provider REST API or SDKAuth
Create a provider API keyCall
model: bytedance/seed-oss-36b-instructModel ID
bytedance/seed-oss-36b-instructRequest example
Curated snippets for this provider are not sourced yet. Use NVIDIA NIM documentation with model ID
bytedance/seed-oss-36b-instruct.Gotchas
- Use provider model ID "bytedance/seed-oss-36b-instruct", not the LLMReference slug "seed-oss-36b-instruct".
Pricing
| Type | Rate |
|---|---|
| GPU Hour Rate | $1.00/GPU·hr |
| GPU Config | 1xH100 |
Capabilities
No model capability flags are currently sourced.
About Seed-OSS 36B Instruct
ByteDance open-source Seed model with 36B parameters.
FAQ
What is the context window for Seed-OSS 36B Instruct on NVIDIA NIM?
Seed-OSS 36B Instruct supports a 4,000 token context window on NVIDIA NIM.
What API model ID do I use for Seed-OSS 36B Instruct on NVIDIA NIM?
Use the model ID bytedance/seed-oss-36b-instruct when calling NVIDIA NIM's API.
Who created Seed-OSS 36B Instruct?
Seed-OSS 36B Instruct was created by ByteDance as part of the Doubao model family.
Is Seed-OSS 36B Instruct open source?
Seed-OSS 36B Instruct is open source according to the seed data.
Model Specs
Released2025-06-01
Parameters36B
Context4K
ArchitectureDecoder Only